Zack Lipton, Fairness, Interpretability and the Dangers of Solutionism (Ethics of AI in Context) | Centre for Ethics, University of Toronto

Centre for Ethics, University of Toronto Search Ethics of AI in Context Fairness, Interpretability and the Dangers of Solutionism Supervised learning algorithms are increasingly operationalized in real-world decision-making systems. Unfortunately, the nature and desiderata of real-world tasks rarely fit neatly into the supervised learning contract. Real data deviates from the training distribution, training targets are often weak surrogates for real-world desiderata, error is seldom the righ

2 mentions: @zacharylipton@UofTEthics
Keywords: fairness
Date: 2020/01/15 05:21

Referring Tweets

@zacharylipton Looking forward to speaking at U of Toronto Centre for Ethics ***today at 4p*** on fairness and interpretability and the dangerous tendency towards naive solutionism and impoverished definitions. See latest paper w @sinafazelpour:
@UofTEthics Tomorrow, @zacharylipton explores the consequences and limitations of employing machine learning based technology in the real world and contemplates the meta-question: when should (today’s) ML systems be off the table altogether? #EthicsofAI Register:

Related Entries

Read more Home - COVIDcast - Delphi Research Group - Carnegie Mellon University
0 users, 1 mentions 2020/06/19 15:51
Read more Learning to Deceive with Attention-Based Explanations - ACL Anthology
0 users, 1 mentions 2020/07/07 23:21
Read more Ray Tune & Weights and Biases: Simple Developer Tools for Scaling Machine Learning | by Kai Fricke |...
0 users, 2 mentions 2020/08/13 13:00
Read more Is it too late to get into Machine Learning - YouTube
0 users, 1 mentions 2020/08/16 03:51
Read more [1802.03916] Detecting and Correcting for Label Shift with Black Box Predictorsopen searchopen navig...
0 users, 2 mentions 2020/09/21 12:59